Q15 saturation limits the result to the range [INT16_MIN, INT16_MAX].
Signed-off-by: LIU Zhiwei <zhiwei_...@c-sky.com>
---
target/riscv/helper.h | 10 ++
target/riscv/insn32.decode | 10 ++
target/riscv/insn_trans/trans_rvp.c.inc | 19 ++++
target/riscv/packed_helper.c | 139 ++++++++++++++++++++++++
4 files changed, 178 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index d992859747..5edaf389e4 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1443,3 +1443,13 @@ DEF_HELPER_3(umin32, i64, env, i64, i64)
DEF_HELPER_3(smax32, i64, env, i64, i64)
DEF_HELPER_3(umax32, i64, env, i64, i64)
DEF_HELPER_2(kabs32, tl, env, tl)
+
+DEF_HELPER_3(khmbb16, i64, env, i64, i64)
+DEF_HELPER_3(khmbt16, i64, env, i64, i64)
+DEF_HELPER_3(khmtt16, i64, env, i64, i64)
+DEF_HELPER_3(kdmbb16, i64, env, i64, i64)
+DEF_HELPER_3(kdmbt16, i64, env, i64, i64)
+DEF_HELPER_3(kdmtt16, i64, env, i64, i64)
+DEF_HELPER_4(kdmabb16, tl, env, tl, tl, tl)
+DEF_HELPER_4(kdmabt16, tl, env, tl, tl, tl)
+DEF_HELPER_4(kdmatt16, tl, env, tl, tl, tl)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index ee5f855f28..a7b5643d5f 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -1066,3 +1066,13 @@ umin32 1010000 ..... ..... 010 ..... 1110111 @r
smax32 1001001 ..... ..... 010 ..... 1110111 @r
umax32 1010001 ..... ..... 010 ..... 1110111 @r
kabs32 1010110 10010 ..... 000 ..... 1110111 @r2
+
+khmbb16 1101110 ..... ..... 001 ..... 1110111 @r
+khmbt16 1110110 ..... ..... 001 ..... 1110111 @r
+khmtt16 1111110 ..... ..... 001 ..... 1110111 @r
+kdmbb16 1101101 ..... ..... 001 ..... 1110111 @r
+kdmbt16 1110101 ..... ..... 001 ..... 1110111 @r
+kdmtt16 1111101 ..... ..... 001 ..... 1110111 @r
+kdmabb16 1101100 ..... ..... 001 ..... 1110111 @r
+kdmabt16 1110100 ..... ..... 001 ..... 1110111 @r
+kdmatt16 1111100 ..... ..... 001 ..... 1110111 @r
diff --git a/target/riscv/insn_trans/trans_rvp.c.inc
b/target/riscv/insn_trans/trans_rvp.c.inc
index 77586e07e4..aa97161697 100644
--- a/target/riscv/insn_trans/trans_rvp.c.inc
+++ b/target/riscv/insn_trans/trans_rvp.c.inc
@@ -1103,3 +1103,22 @@ static bool trans_##NAME(DisasContext *s, arg_r2 *a) \
}
GEN_RVP64_R2_OOL(kabs32);
+
+/* (RV64 Only) SIMD Q15 saturating Multiply Instructions */
+GEN_RVP64_R_OOL(khmbb16);
+GEN_RVP64_R_OOL(khmbt16);
+GEN_RVP64_R_OOL(khmtt16);
+GEN_RVP64_R_OOL(kdmbb16);
+GEN_RVP64_R_OOL(kdmbt16);
+GEN_RVP64_R_OOL(kdmtt16);
+
+#define GEN_RVP64_R_ACC_OOL(NAME) \
+static bool trans_##NAME(DisasContext *s, arg_r *a) \
+{ \
+ REQUIRE_64BIT(s); \
+ return r_acc_ool(s, a, gen_helper_##NAME); \
+}
+
+GEN_RVP64_R_ACC_OOL(kdmabb16);
+GEN_RVP64_R_ACC_OOL(kdmabt16);
+GEN_RVP64_R_ACC_OOL(kdmatt16);
diff --git a/target/riscv/packed_helper.c b/target/riscv/packed_helper.c
index a808dae9d8..32e0af2ef6 100644
--- a/target/riscv/packed_helper.c
+++ b/target/riscv/packed_helper.c
@@ -3422,3 +3422,142 @@ static inline void do_kabs32(CPURISCVState *env, void
*vd, void *va, uint8_t i)
}
RVPR2(kabs32, 1, 4);
+
+/* (RV64 Only) SIMD Q15 saturating Multiply Instructions */
+static inline void do_khmbb16(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int32_t *d = vd;
+ int16_t *a = va, *b = vb;
+
+ d[H4(i / 2)] = sat64(env, (int64_t)a[H2(i)] * b[H2(i)] >> 15, 15);
+}
+
+RVPR64_64_64(khmbb16, 2, 2);
+
+static inline void do_khmbt16(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int32_t *d = vd;
+ int16_t *a = va, *b = vb;
+
+ d[H4(i / 2)] = sat64(env, (int64_t)a[H2(i)] * b[H2(i + 1)] >> 15, 15);
+}
+
+RVPR64_64_64(khmbt16, 2, 2);
+
+static inline void do_khmtt16(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int32_t *d = vd;
+ int16_t *a = va, *b = vb;
+
+ d[H4(i / 2)] = sat64(env, (int64_t)a[H2(i + 1)] * b[H2(i + 1)] >> 15, 15);
+}
+
+RVPR64_64_64(khmtt16, 2, 2);
+
+static inline void do_kdmbb16(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int32_t *d = vd;
+ int16_t *a = va, *b = vb;
+
+ if (a[H2(i)] == INT16_MIN && b[H2(i)] == INT16_MIN) {
+ d[H4(i / 2)] = INT32_MAX;
+ env->vxsat = 0x1;
+ } else {
+ d[H4(i / 2)] = (int64_t)a[H2(i)] * b[H2(i)] << 1;
+ }
+}
+
+RVPR64_64_64(kdmbb16, 2, 2);
+
+static inline void do_kdmbt16(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int32_t *d = vd;
+ int16_t *a = va, *b = vb;
+
+ if (a[H2(i)] == INT16_MIN && b[H2(i + 1)] == INT16_MIN) {
+ d[H4(i / 2)] = INT32_MAX;
+ env->vxsat = 0x1;
+ } else {
+ d[H4(i / 2)] = (int64_t)a[H2(i)] * b[H2(i + 1)] << 1;
+ }
+}
+
+RVPR64_64_64(kdmbt16, 2, 2);
+
+static inline void do_kdmtt16(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int32_t *d = vd;
+ int16_t *a = va, *b = vb;
+
+ if (a[H2(i + 1)] == INT16_MIN && b[H2(i + 1)] == INT16_MIN) {
+ d[H4(i / 2)] = INT32_MAX;
+ env->vxsat = 0x1;
+ } else {
+ d[H4(i / 2)] = (int64_t)a[H2(i + 1)] * b[H2(i + 1)] << 1;
+ }
+}
+
+RVPR64_64_64(kdmtt16, 2, 2);
+
+static inline void do_kdmabb16(CPURISCVState *env, void *vd, void *va,
+ void *vb, void *vc, uint8_t i)
+
+{
+ int32_t *d = vd;
+ int16_t *a = va, *b = vb;
+ int32_t *c = vc, m0;
+
+ if (a[H2(i)] == INT16_MIN && b[H2(i)] == INT16_MIN) {
+ m0 = INT32_MAX;
+ env->vxsat = 0x1;
+ } else {
+ m0 = (int32_t)a[H2(i)] * b[H2(i)] << 1;
+ }
+ d[H4(i / 2)] = sadd32(env, 0, c[H4(i / 2)], m0);
+}
+
+RVPR_ACC(kdmabb16, 2, 2);
+
+static inline void do_kdmabt16(CPURISCVState *env, void *vd, void *va,
+ void *vb, void *vc, uint8_t i)
+
+{
+ int32_t *d = vd;
+ int16_t *a = va, *b = vb;
+ int32_t *c = vc, m0;
+
+ if (a[H2(i)] == INT16_MIN && b[H2(i + 1)] == INT16_MIN) {
+ m0 = INT32_MAX;
+ env->vxsat = 0x1;
+ } else {
+ m0 = (int32_t)a[H2(i)] * b[H2(i + 1)] << 1;
+ }
+ d[H4(i / 2)] = sadd32(env, 0, c[H4(i / 2)], m0);
+}
+
+RVPR_ACC(kdmabt16, 2, 2);
+
+static inline void do_kdmatt16(CPURISCVState *env, void *vd, void *va,
+ void *vb, void *vc, uint8_t i)
+
+{
+ int32_t *d = vd;
+ int16_t *a = va, *b = vb;
+ int32_t *c = vc, m0;
+
+ if (a[H2(i + 1)] == INT16_MIN && b[H2(i + 1)] == INT16_MIN) {
+ m0 = INT32_MAX;
+ env->vxsat = 0x1;
+ } else {
+ m0 = (int32_t)a[H2(i + 1)] * b[H2(i + 1)] << 1;
+ }
+ d[H4(i / 2)] = sadd32(env, 0, c[H4(i / 2)], m0);
+}
+
+RVPR_ACC(kdmatt16, 2, 2);
--
2.25.1
